Introduction – Gnani Speech APIs - Gnani AI Documentation

Build with Gnani Speech APIs when you need transcription or synthesis in production — REST for short clips, WebSocket for live audio, and Batch for long or multi-file jobs.

Product	When to use it
This section	Integrate STT, TTS, or voice cloning directly in your app
Agent Builder	Configure agents in the console
Agent Builder Platform API	Manage agents, FAQs, and conversations over REST

Base URL

https://api.vachana.ai

All paths in this documentation are relative to this base URL.

Authentication

Send your API key on every request:

X-API-Key-ID: <your_api_key>

Generate a key from the Gnani API dashboard. Missing or invalid keys return 401 Unauthorized.

Store keys in environment variables or a secrets manager. Do not commit them to source control.

Available APIs

Speech-to-Text — Gnani Prisma v2.5

API	Best for	Guide
STT REST	Audio up to 60 seconds, single HTTP response	Speech-to-Text REST
STT Realtime	Live microphone or streaming audio	STT Realtime
STT Batch	Long files, many files, offline pipelines	Batch STT

Text-to-Speech — Gnani Timbre v2.5

Timbre v2.5 is the recommended model. Timbre v2.0 is deprecated and will be removed in a future release.

API	Best for	Guide
TTS REST	Full audio in one response	TTS REST
TTS Streaming	Progressive playback via SSE	TTS Streaming
TTS Realtime	Lowest latency over WebSocket	TTS Realtime
Voice catalog	Pick a voice before you integrate	Available Voices

Voice cloning

API	Best for	Guide
VC Embeddings	Create a `speaker_embedding` from reference audio	Voice Clone Embeddings
VC REST	Cloned voice in one HTTP response	VC REST
VC Streaming	Cloned voice over SSE	VC Streaming
VC Realtime	Cloned voice over WebSocket	VC Realtime

Key capabilities

Capability	Details
Languages	10+ Indian languages with native-script output
Audio formats	WAV, MP3, OGG, FLAC, AAC, M4A (STT)
Voice cloning	Clone from a short reference sample
Latency	P95 ~200 ms for STT; streaming TTS supported
Modes	Real-time, REST, and batch
Formatting	Auto-punctuation and text normalization on supported endpoints
SSML	Supported on TTS for fine-grained control

Integrations

Plugin	Guide
LiveKit	LiveKit plugin
Pipecat	Pipecat plugin

Use case guides

Guide	Description
Podcast transcription	Speaker-separated batch transcription
Call analytics	Batch STT plus LLM analysis
Real-time compliance	Live WebSocket monitoring

Get started

New to the APIs? Start here: Quick Start

Docs feedback

Docs feedback: Gnani APIs docs feedback Last verified: 5 August 2026

​Base URL

​Authentication

​Available APIs

​Speech-to-Text — Gnani Prisma v2.5

​Text-to-Speech — Gnani Timbre v2.5

​Voice cloning

​Key capabilities

​Integrations

​Use case guides

​Get started

​Docs feedback

Base URL

Authentication

Available APIs

Speech-to-Text — Gnani Prisma v2.5

Text-to-Speech — Gnani Timbre v2.5

Voice cloning

Key capabilities

Integrations

Use case guides

Get started

Docs feedback